Comments (3)
The meta testing of NegMargin
will build and finetune a new head for each task. Currently, the demo does not support methods that require fine-tuning during testing since the inference codes do not introduce any code of training.
from mmfewshot.
If you only need to test a few tasks, it might work by saving all the pre-trained weights. As for the inference, I think it is possible to compute the weights of fc layer from extracted features mutually since it only trains a linear head.
from mmfewshot.
What if we process support images for the same task as was during training and validation? In this case, a new head won't be needed because it has already been fine-tuned during the meta testing of the training phase. In other words, the head formed during meta-test in training could be directly utilized and the step of fine-tuning a new head skipped. Does this make sense?
Alternatively, do you have any other suggestions to do inference while serving these models (which are performing better for my task) in production?
from mmfewshot.
Related Issues (20)
- About the design of bbox_head of AttentionRPN
- Have you stopped updating mmfewshot?
- Hello, is there any tool in mmfewshot for calculating FLOPs, parameter count, and FPS?
- Add mobilenetv2 as backbone model.
- 运行TFA算法出现nan HOT 2
- cannot import name 'show_result_pyplot' from 'mmdet.apis' HOT 4
- How to make my own dataset in COCO format for MMFewshot?
- 'NoneType' object has no attribute 'update' when running Meta -RCNN HOT 1
- loss are NAN
- Slow training and High memory usage for classification models
- About the data path
- Is this repository still undergoing maintenance and updates?
- persistent_workers
- about fpn
- About Attention-RPN fine-tuning
- 中文版 install RADEME有错误
- tools/classification/test.py has no attribute 'out'
- incompatibility between the versions of mmdet and mmcv HOT 2
- Discrepancy in AP50 while Re-implementing MetaRCNN
- about register NECKS
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mmfewshot.